Design Space and Implementation of RAG-Based Avatars for Virtual Archaeology

TL;DR

This paper explores the design and implementation of retrieval-augmented generation (RAG) avatars in virtual reality for digital heritage, demonstrating their potential to enhance user engagement and access to archaeological information.

Contribution

It introduces a comprehensive design space for RAG avatars in virtual environments and evaluates their effectiveness in providing cultural heritage information.

Findings

Users perceive low workload when interacting with RAG avatars.

RAG avatars increase topical engagement in virtual archaeology.

The system provides high-quality, on-demand information about heritage objects.

Abstract

Immersive technologies, such as virtual and augmented reality, are transforming digital heritage by enabling users to explore and interact with culturally significant sites. It is now possible to view and augment digital twins, or digitally reconstructed versions of them, and to enable access to previously unreachable locations for a broader audience. Here, we investigate retrieval-augmented generation (RAG)-based avatars as an interface for accessing further information about digital cultural heritage objects while immersed in dedicated virtual environments. We present a requirement design space that spans the application realm, avatar personality, and I/O modalities. We instantiate it with a RAG system coupled to a conversational avatar in a virtual reality (VR) environment, using the Maxentius mausoleum from the 4th century AD as a case study, through which users gain access to curated on-demand information of the digitised heritage object. Our workflow utilises scholarly texts and enriches them with metadata. We evaluate various RAG configurations in terms of answer quality on a small expert-crafted question-answer set, as well as the perceived workload of users of a VR setup using such a RAG avatar. We demonstrate evidence that users perceive the overall workload for interacting with such an avatar as below average and that such avatars help to gain topical engagement. Overall, our work demonstrates how to utilise RAG-driven VR avatars for archaeological purposes and provides evidence that they can offer a pathway for immersive, AI-enhanced digital heritage applications.